Zobrazeno 1 - 10
of 6 469
pro vyhledávání: '"WEI Xian"'
Autor:
Shen, Xiangxiang, Wan, Zheng, Wen, Lingfeng, Sun, Licheng, Jie, Ou Yang Ming, Tang, Xuan, Zeng, Xian, Chen, Mingsong, He, Xiao, Wei, Xian
To date, the International Zeolite Association Structure Commission (IZA-SC) has cataloged merely 255 distinct zeolite structures, with millions of theoretically possible structures yet to be discovered. The synthesis of a specific zeolite typically
Externí odkaz:
http://arxiv.org/abs/2408.12984
Autor:
Wu, Zhiqiang, Sun, Licheng, Liu, Yingjie, Yang, Jian, Dong, Hanlin, Lin, Shing-Ho J., Tang, Xuan, Mi, Jinpeng, Jin, Bo, Wei, Xian
Group Equivariant Convolution (GConv) can effectively handle rotational symmetry data. They assume uniform and strict rotational symmetry across all features, as the transformations under the specific group. However, real-world data rarely conforms t
Externí odkaz:
http://arxiv.org/abs/2408.12454
Autor:
Wu, Zhiqiang, Liu, Yingjie, Dong, Hanlin, Tang, Xuan, Yang, Jian, Jin, Bo, Chen, Mingsong, Wei, Xian
Introducing Group Equivariant Convolution (GConv) empowers models to explore symmetries hidden in visual data, improving their performance. However, in real-world scenarios, objects or scenes often exhibit perturbations of a symmetric system, specifi
Externí odkaz:
http://arxiv.org/abs/2408.11760
Although Federated Learning (FL) enables collaborative learning in Artificial Intelligence of Things (AIoT) design, it fails to work on low-memory AIoT devices due to its heavy memory usage. To address this problem, various federated pruning methods
Externí odkaz:
http://arxiv.org/abs/2405.04765
Non-Euclidean data is frequently encountered across different fields, yet there is limited literature that addresses the fundamental challenge of training neural networks with manifold representations as outputs. We introduce the trick named Deep Ext
Externí odkaz:
http://arxiv.org/abs/2404.00544
Autor:
Si, Yangyang, Zhang, Tianfu, Liu, Chenhan, Das, Sujit, Xu, Bin, Burkovsky, Roman G, Wei, Xian-Kui, Chen, Zuhuang
Antiferroelectrics have received blooming interests because of a wide range of potential applications in energy storage, solid-state cooling, thermal switch, transducer, actuation, and memory devices. Many of those applications are the most prospecti
Externí odkaz:
http://arxiv.org/abs/2312.16806
Autor:
Wei, Xian-Kui, Jalil, Abdur Rehman, Rüßmann, Philipp, Ando, Yoichi, Grützmacher, Detlev, Blügel, Stefan, Mayer, Joachim
The proximity effect at a highly transparent interface of an s-wave superconductor (S) and a topological insulator (TI) provides a promising platform to create Majorana zero modes in artificially designed heterostructures. However, structural and che
Externí odkaz:
http://arxiv.org/abs/2311.16590
Autor:
Jessica, Loh Sher En, Arafat, Naheed Anjum, Lim, Wei Xian, Chan, Wai Lee, Kong, Adams Wai Kin
Computational fluid dynamics (CFD) simulation is an irreplaceable modelling step in many engineering designs, but it is often computationally expensive. Some graph neural network (GNN)-based CFD methods have been proposed. However, the current method
Externí odkaz:
http://arxiv.org/abs/2311.14464
Due to the popularity of Artificial Intelligence (AI) technology, numerous backdoor attacks are designed by adversaries to mislead deep neural network predictions by manipulating training samples and training processes. Although backdoor attacks are
Externí odkaz:
http://arxiv.org/abs/2310.11595
In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual learning. To reduce forgetting, some existing rehearsal-based methods us
Externí odkaz:
http://arxiv.org/abs/2310.08038